Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 770 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.4861. Min Act: -0.1700
Data Index: 7671412 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.4705. Min Act: -0.1700
Data Index: 7121765 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.3607. Min Act: -0.1700
Data Index: 510295 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.3607. Min Act: -0.1700
Data Index: 454986 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.3451. Min Act: -0.1700
Data Index: 6570645 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.3451. Min Act: -0.1700
Data Index: 8485493 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.3137. Min Act: -0.1700
Data Index: 6822197 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.2980. Min Act: -0.1700
Data Index: 1088839 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.3137. Min Act: -0.1700
Data Index: 1548289 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.3137. Min Act: -0.1700
Data Index: 1327800 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.2980. Min Act: -0.1700
Data Index: 4871613 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.2980. Min Act: -0.1700
Data Index: 127616 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.2980. Min Act: -0.1700
Data Index: 1407267 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.2980. Min Act: -0.1700
Data Index: 1327799 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.3137. Min Act: -0.1700
Data Index: 8062122 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.2666. Min Act: -0.1700
Data Index: 6786008 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.2823. Min Act: -0.1700
Data Index: 2382257 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.2666. Min Act: -0.1700
Data Index: 811242 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.2666. Min Act: -0.1700
Data Index: 6457690 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4861. Min Range: -3.4861
Max Act: 3.2823. Min Act: -0.1700
Data Index: 2236883 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19